CN111775151A - Intelligent control system of robot - Google Patents
Intelligent control system of robot Download PDFInfo
- Publication number
- CN111775151A CN111775151A CN202010598446.4A CN202010598446A CN111775151A CN 111775151 A CN111775151 A CN 111775151A CN 202010598446 A CN202010598446 A CN 202010598446A CN 111775151 A CN111775151 A CN 111775151A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- module
- robot
- voice
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000009471 action Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 230000002457 bidirectional effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000010408 sweeping Methods 0.000 claims description 9
- 241000282414 Homo sapiens Species 0.000 claims description 7
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 6
- 230000000873 masking effect Effects 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000000750 progressive effect Effects 0.000 claims description 6
- 230000000306 recurrent effect Effects 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 210000005069 ears Anatomy 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/003—Controls for manipulators by means of an audio-responsive input
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
Abstract
The invention belongs to the technical field of robots, and discloses an intelligent control system of a robot, which comprises: the system comprises a camera module, a voice acquisition module, a control parameter setting module, a central control module, a wireless control module, a voice recognition module, an image recognition module, an execution module, an obstacle avoidance module, a position positioning module, a storage module, a voice prompt module and a display module. According to the invention, the voice command recognition accuracy can be greatly improved through the voice recognition module, when the robot detects an obstacle, the obstacle avoidance module acquires the parameter information of the obstacle, and controls the robot to execute the obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot; the robot can be controlled to execute the obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot, the obstacle avoidance capability of the robot is favorably improved, and the robot has high usability and practicability.
Description
Technical Field
The invention belongs to the technical field of robots, and particularly relates to an intelligent control system of a robot.
Background
The Robot (Robot) is an intelligent machine capable of working semi-autonomously or fully autonomously, has basic characteristics of perception, decision, execution and the like, can assist or even replace human beings to finish dangerous, heavy and complex work, improves the working efficiency and quality, serves human life, and expands or extends the activity and capability range of the human beings. As people's understanding of the intelligent nature of robotics has deepened, robotics has begun to continually infiltrate into various areas of human activity. In combination with the application characteristics in these fields, people develop various special robots and various intelligent robots with sensing, decision-making, action and interaction capabilities.
Under the rapid development of science and technology, a series of high and new technologies are needed to control the robot in the research and development process of the robot, and various technical advantages are combined. The mutual fusion of the free control cross idea and the artificial intelligence is the theoretical basis of intelligent control, and the control system comprises three control systems of artificial control, machine control and joint control of the artificial control and the machine control. The classification, distribution and openness are the main characteristics of the intelligent control system, and if the powerful comprehensive information processing capability is applied to the intelligent development of the robot, the rapid development of the robot field can be promoted.
However, the existing robot intelligent control system is inaccurate in voice instruction identification; meanwhile, the obstacle cannot be effectively avoided. And the existing robots are different in use environment and inconvenient to control through a single control mode.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) the existing robot intelligent control system has inaccurate recognition on voice commands; meanwhile, the obstacle cannot be effectively avoided.
(2) The existing robot has different use environments and is inconvenient to control through a single control mode.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent control system for a robot.
The invention is realized in this way, an intelligent control system for a robot includes:
the camera module is connected with the central control module and used for acquiring images at a specified angle through the camera according to the control instruction;
the voice acquisition module is connected with the central control module and is used for acquiring voice instructions through a voice acquisition device embedded outside the robot;
the control parameter setting module is connected with the central control module and used for configuring the control parameters of the robot through a parameter configuration program;
the central control module is connected with the camera module, the voice acquisition module, the control parameter setting module, the wireless control module, the voice recognition module, the image recognition module, the execution module, the obstacle avoidance module, the position positioning module, the storage module, the voice prompt module and the display module, and is used for processing the acquired information through the main controller and controlling the normal work of each module through preset parameters and processing results;
the wireless control module is connected with the central control module and used for carrying out data interaction with the remote control terminal through the wireless signal transmitter so as to carry out wireless remote control;
the voice recognition module is connected with the central control module and used for receiving the collected voice instruction information and recognizing the voice instruction through a voice recognizer;
the image identification module is connected with the central control module and used for identifying the collected image through an image identification program and determining an action instruction corresponding to the image;
the execution module is connected with the central control module and is used for working according to the voice command and the action command through the execution mechanism;
the obstacle avoidance module is connected with the central control module and used for detecting obstacle information and avoiding obstacles encountered by the robot through the obstacle avoidance mechanism;
the position positioning module is connected with the central control module and used for constructing a three-dimensional view of the surrounding environment of the position where the position positioning module is located by acquiring images and marking the position point of the position positioning module in the three-dimensional view;
the storage module is connected with the central control module and used for storing the preset information and the acquired data through the memory;
the voice prompt module is connected with the central control module and used for carrying out voice playing on the received information and the running state through the voice broadcaster;
and the display module is connected with the central control module and used for displaying the acquired images and voice instructions through the display screen.
Further, the camera module includes:
the image acquisition unit is used for acquiring images through the camera;
the illumination compensation unit is used for synchronously moving with the camera through the LED light supplement lamp and performing illumination compensation on the image acquisition position of the camera;
and the angle adjusting unit is used for connecting the camera with the robot main body and adjusting and controlling the orientation of the lens of the camera through the angle adjusting device.
Further, the image recognition module includes:
the preset information storage unit is used for pre-storing the specific limb action image information to obtain a data set;
the characteristic extraction unit is used for extracting the characteristics of the limb action information in the collected image information;
and the instruction judging unit is used for comparing the extracted body action information characteristics with preset information in a preset data set, determining action instruction information corresponding to the extracted body action information characteristics, and outputting the action instruction information to the central control module.
Further, the position location module includes:
the three-dimensional view construction unit is used for collecting surrounding images through the camera when the robot is placed in a new environment to construct a three-dimensional view;
the position image identification unit is used for comparing the acquired environment image of the real-time position with the image in the constructed three-dimensional view to determine the position of the robot;
and the position point marking unit is used for marking position points in the three-dimensional view according to the real-time position of the robot and transmitting the position points to the remote monitoring terminal through wireless signals.
Further, the speech recognition module recognition method is as follows:
(1) extracting acoustic characteristics of each voice frame; training a progressive double-output neural network model by using samples of clean voice and noise voice, estimating ideal soft masking of each voice frame by using the trained progressive double-output neural network model, and performing enhancement processing on acoustic characteristics; if the method is applied to human ears, the waveform is reconstructed by using the enhanced acoustic features to obtain a waveform capable of being subjectively listened; if the method is applied to a voice recognition system, applying the estimated ideal soft masking to the acoustic features of the input voice to obtain masked acoustic features, and then reconstructing the waveform to obtain enhanced voice;
(2) acquiring an original learning data set relating to the recognition target language, wherein each original learning data included in the original learning data set includes learning-use voice data and text information corresponding to the learning-use voice data; constructing a target tag by separating text information included in the respective original learning data in units of letters;
(3) an acoustic model based on a deep neural network is constructed by learning speech data for learning and a target label corresponding to the learning speech data included in the respective pieces of original learning data, wherein different letters among the letters included in the target label are defined as classes different from each other in the acoustic model, and even if the same letter is included, the same letter is defined as a class different from each other when the arrangement position is different.
Further, the target tag contains a score, the score contained in the textual information, wherein the score is defined in the acoustic model as a separate class.
Further, the step of constructing the acoustic model comprises:
(3.1) updating the weighting values of the deep neural network constituting the acoustic model using a connection timing classification method;
(3.2) the deep neural network comprises at least one of a recurrent neural network, a bidirectional recurrent neural network, a long-short term memory, a bidirectional long-short term memory, a gated cyclic unit, and a bidirectional gated cyclic unit.
Further, the obstacle avoidance module obstacle avoidance method comprises the following steps:
1) when the robot detects that an obstacle exists, acquiring parameter information of the obstacle; determining a first height value and a second height value of the obstacle, wherein the first height value is the distance between the highest point of one end, close to the robot, of the obstacle and the ground, and the second height value is the distance between the highest point of one end, far away from the robot, of the obstacle and the ground;
2) and controlling the robot to execute obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot according to the parameter information of the obstacle, the size relation between the first height value and the preset threshold value, and the size relation between the second height value and the preset threshold value, and the current working mode of the robot.
Further, the controlling the robot to execute an obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot according to the size relationship among the parameter information of the obstacle, the first height value, the second height value and the preset threshold value and the current working mode of the robot includes:
2.1) determining the type of the obstacle according to the parameter information of the obstacle, the size relationship between the first height value and the preset threshold value, the size relationship between the second height value and the preset threshold value and the current working mode of the robot;
2.2) controlling the robot to execute obstacle avoidance operation corresponding to the type of the obstacle according to the determined type of the obstacle.
Further, the determining the type of the obstacle according to the magnitude relation between the parameter information of the obstacle, the first height value, the second height value and the preset threshold value and the current working mode of the robot includes:
when the current working mode of the robot is a mopping mode or a sweeping and mopping integrated mode, if the height of the obstacle is smaller than a first preset height, the type of the obstacle is determined to be a stridable obstacle, and if the height of the obstacle is larger than or equal to the first preset height, the type of the obstacle is determined to be a non-stridable obstacle.
Further, the determining the type of the obstacle according to the magnitude relation between the parameter information of the obstacle, the first height value, the second height value and the preset threshold value and the current working mode of the robot further includes:
when the current working mode of the robot is a mopping mode or a sweeping and mopping integrated mode, if the inclination angle of the obstacle is smaller than a first preset angle, determining that the type of the obstacle is a stridable obstacle, and if the inclination angle of the obstacle is larger than or equal to the first preset angle, determining that the type of the obstacle is a non-stridable obstacle.
Further, the determining the type of the obstacle according to the magnitude relation between the parameter information of the obstacle, the first height value, the second height value and the preset threshold value and the current working mode of the robot further includes:
when the current working mode of the robot is a sweeping mode, if the height of the obstacle is smaller than a second preset height, determining that the type of the obstacle is a stridable obstacle, and if the height of the obstacle is larger than or equal to the second preset height, determining that the type of the obstacle is a non-stridable obstacle.
The invention has the advantages and positive effects that: according to the invention, the voice command recognition accuracy can be greatly improved through the voice recognition module, and meanwhile, when the robot detects an obstacle, the obstacle avoidance module acquires the parameter information of the obstacle and controls the robot to execute the obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot; the robot can be controlled to execute the obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot, the obstacle avoidance capability of the robot is favorably improved, and the robot has high usability and practicability.
The invention can realize remote control, voice control and limb action control through the voice recognition module and the image recognition module, has various functions, can perform voice control in a dark state, and can perform limb action control in a noise environment, thereby being suitable for various occasions.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
Fig. 1 is a block diagram of a robot intelligent control system according to an embodiment of the present invention.
In the figure: 1. a camera module; 2. a voice acquisition module; 3. a control parameter setting module; 4. a central control module; 5. a wireless control module; 6. a voice recognition module; 7. an image recognition module; 8. an execution module; 9. an obstacle avoidance module; 10. a position location module; 11. a storage module; 12. a voice prompt module; 13. and a display module.
Fig. 2 is a flowchart of a speech recognition module recognition method according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for constructing the acoustic model according to an embodiment of the present invention.
Fig. 4 is a flowchart of an obstacle avoidance method of an obstacle avoidance module according to an embodiment of the present invention.
Fig. 5 is a block diagram of a camera module according to an embodiment of the present invention.
Fig. 6 is a block diagram of an image recognition module according to an embodiment of the present invention.
Fig. 7 is a block diagram of a position location module according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In order to solve the problems in the prior art, the present invention provides an intelligent robot control system, which is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, an intelligent robot control system according to an embodiment of the present invention includes: the system comprises a camera module 1, a voice acquisition module 2, a control parameter setting module 3, a central control module 4, a wireless control module 5, a voice recognition module 6, an image recognition module 7, an execution module 8, an obstacle avoidance module 9, a position positioning module 10, a storage module 11, a voice prompt module 12 and a display module 13.
The camera module 1 is connected with the central control module and used for collecting images at a specified angle through a camera according to a control instruction;
the voice acquisition module 2 is connected with the central control module and is used for acquiring voice instructions through a voice acquisition device embedded outside the robot;
the control parameter setting module 3 is connected with the central control module and is used for configuring the control parameters of the robot through a parameter configuration program;
the central control module 4 is connected with the camera module, the voice acquisition module, the control parameter setting module, the wireless control module, the voice recognition module, the image recognition module, the execution module, the obstacle avoidance module, the position positioning module, the storage module, the voice prompt module and the display module, and is used for processing the acquired information through the main controller and controlling the normal work of each module through preset parameters and processing results;
the wireless control module 5 is connected with the central control module and used for carrying out data interaction with a remote control terminal through a wireless signal transmitter so as to carry out wireless remote control;
the voice recognition module 6 is connected with the central control module and is used for receiving the collected voice instruction information and recognizing the voice instruction through a voice recognizer;
the image identification module 7 is connected with the central control module and is used for identifying the collected image through an image identification program and determining an action instruction corresponding to the image;
the execution module 8 is connected with the central control module and is used for working according to the voice command and the action command through an execution mechanism;
the obstacle avoidance module 9 is connected with the central control module, and is used for detecting obstacle information and avoiding obstacles encountered by the robot through an obstacle avoidance mechanism;
the position positioning module 10 is connected with the central control module and used for constructing a three-dimensional view of the surrounding environment of the position where the position positioning module is located by acquiring images and marking the position point of the position positioning module in the three-dimensional view;
the storage module 11 is connected with the central control module and used for storing preset information and acquired data through a memory;
the voice prompt module 12 is connected with the central control module and used for carrying out voice playing on the received information and the running state through a voice broadcaster;
and the display module 13 is connected with the central control module and is used for displaying the acquired images and voice instructions through a display screen.
As shown in fig. 2, the speech recognition module 6 provided in the embodiment of the present invention has the following recognition method:
s101, extracting acoustic characteristics of each voice frame; training a progressive double-output neural network model by using samples of clean voice and noise voice, estimating ideal soft masking of each voice frame by using the trained progressive double-output neural network model, and performing enhancement processing on acoustic characteristics; if the method is applied to human ears, the waveform is reconstructed by using the enhanced acoustic features to obtain a waveform capable of being subjectively listened; if the method is applied to a voice recognition system, applying the estimated ideal soft masking to the acoustic features of the input voice to obtain masked acoustic features, and then reconstructing the waveform to obtain enhanced voice;
s102, acquiring an original learning data group related to the language to be recognized, wherein each original learning data included in the original learning data group includes learning voice data and text information corresponding to the learning voice data; constructing a target tag by separating text information included in the respective original learning data in units of letters;
and S103, learning the learning voice data contained in each original learning data and a target label corresponding to the learning voice data to construct an acoustic model based on the deep neural network, wherein different letters among the letters contained in the target label are defined as different classes in the acoustic model, and even if the same letter is arranged at different positions, the different classes are defined as different classes.
The target tag provided by the invention comprises a write, which is contained in the text information, wherein the write is defined as a separate class in the acoustic model.
As shown in fig. 3, the step of constructing the acoustic model provided by the embodiment of the present invention includes:
s201, updating the weighted value of the deep neural network forming the acoustic model by using a connection time sequence classification method;
s202, the deep neural network comprises at least one of a recurrent neural network, a bidirectional recurrent neural network, a long-short term memory, a bidirectional long-short term memory, a gated cyclic unit and a bidirectional gated cyclic unit.
As shown in fig. 4, an obstacle avoidance method of the obstacle avoidance module 9 provided in the embodiment of the present invention is as follows:
s301, when the robot detects that an obstacle exists, acquiring parameter information of the obstacle; determining a first height value and a second height value of the obstacle, wherein the first height value is the distance between the highest point of one end, close to the robot, of the obstacle and the ground, and the second height value is the distance between the highest point of one end, far away from the robot, of the obstacle and the ground;
s302, controlling the robot to execute obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot according to the parameter information of the obstacle, the first height value, the size relation between the second height value and the preset threshold value and the current working mode of the robot.
According to the parameter information of the obstacle, the first height value, the magnitude relation between the second height value and the preset threshold value and the current working mode of the robot, the method for controlling the robot to execute obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot comprises the following steps:
determining the type of the obstacle according to the parameter information of the obstacle, the size relationship between the first height value and the preset threshold value, the size relationship between the second height value and the preset threshold value, and the current working mode of the robot;
and controlling the robot to execute obstacle avoidance operation corresponding to the type of the obstacle according to the determined type of the obstacle.
The invention provides parameter information of the obstacle, a first height value, a size relation between a second height value and a preset threshold value and a current working mode of the robot, and the determination of the type of the obstacle comprises the following steps:
when the current working mode of the robot is a mopping mode or a sweeping and mopping integrated mode, if the height of the obstacle is smaller than a first preset height, the type of the obstacle is determined to be a stridable obstacle, and if the height of the obstacle is larger than or equal to the first preset height, the type of the obstacle is determined to be a non-stridable obstacle.
The determining the type of the obstacle according to the parameter information of the obstacle, the magnitude relation between the first height value and the preset threshold value, the magnitude relation between the second height value and the preset threshold value, and the current working mode of the robot provided by the invention further comprises:
when the current working mode of the robot is a mopping mode or a sweeping and mopping integrated mode, if the inclination angle of the obstacle is smaller than a first preset angle, determining that the type of the obstacle is a stridable obstacle, and if the inclination angle of the obstacle is larger than or equal to the first preset angle, determining that the type of the obstacle is a non-stridable obstacle.
The determining the type of the obstacle according to the parameter information of the obstacle, the magnitude relation between the first height value and the preset threshold value, the magnitude relation between the second height value and the preset threshold value, and the current working mode of the robot provided by the invention further comprises:
when the current working mode of the robot is a sweeping mode, if the height of the obstacle is smaller than a second preset height, determining that the type of the obstacle is a stridable obstacle, and if the height of the obstacle is larger than or equal to the second preset height, determining that the type of the obstacle is a non-stridable obstacle.
As shown in fig. 5, a camera module 1 according to an embodiment of the present invention includes:
the image acquisition unit is used for acquiring images through the camera;
the illumination compensation unit is used for synchronously moving with the camera through the LED light supplement lamp and performing illumination compensation on the image acquisition position of the camera;
and the angle adjusting unit is used for connecting the camera with the robot main body and adjusting and controlling the orientation of the lens of the camera through the angle adjusting device.
As shown in fig. 6, the image recognition module 7 according to the embodiment of the present invention includes:
the preset information storage unit is used for pre-storing the specific limb action image information to obtain a data set;
the characteristic extraction unit is used for extracting the characteristics of the limb action information in the collected image information;
and the instruction judging unit is used for comparing the extracted body action information characteristics with preset information in a preset data set, determining action instruction information corresponding to the extracted body action information characteristics, and outputting the action instruction information to the central control module.
As shown in fig. 7, the position locating module 10 provided in the embodiment of the present invention includes:
the three-dimensional view construction unit is used for collecting surrounding images through the camera when the robot is placed in a new environment to construct a three-dimensional view;
the position image identification unit is used for comparing the acquired environment image of the real-time position with the image in the constructed three-dimensional view to determine the position of the robot;
and the position point marking unit is used for marking position points in the three-dimensional view according to the real-time position of the robot and transmitting the position points to the remote monitoring terminal through wireless signals.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope of the present invention disclosed herein, which is within the spirit and principle of the present invention, should be covered by the present invention.
Claims (9)
1. A robot intelligence control system, comprising:
the camera module is connected with the central control module and used for acquiring images at a specified angle through the camera according to the control instruction;
the voice acquisition module is connected with the central control module and is used for acquiring voice instructions through a voice acquisition device embedded outside the robot;
the control parameter setting module is connected with the central control module and used for configuring the control parameters of the robot through a parameter configuration program;
the central control module is connected with the camera module, the voice acquisition module, the control parameter setting module, the wireless control module, the voice recognition module, the image recognition module, the execution module, the obstacle avoidance module, the position positioning module, the storage module, the voice prompt module and the display module, and is used for processing the acquired information through the main controller and controlling the normal work of each module through preset parameters and processing results;
the wireless control module is connected with the central control module and used for carrying out data interaction with the remote control terminal through the wireless signal transmitter so as to carry out wireless remote control;
the voice recognition module is connected with the central control module and used for receiving the collected voice instruction information and recognizing the voice instruction through a voice recognizer;
the image identification module is connected with the central control module and used for identifying the collected image through an image identification program and determining an action instruction corresponding to the image;
the execution module is connected with the central control module and is used for working according to the voice command and the action command through the execution mechanism;
the obstacle avoidance module is connected with the central control module and used for detecting obstacle information and avoiding obstacles encountered by the robot through the obstacle avoidance mechanism;
the position positioning module is connected with the central control module and used for constructing a three-dimensional view of the surrounding environment of the position where the position positioning module is located by acquiring images and marking the position point of the position positioning module in the three-dimensional view;
the storage module is connected with the central control module and used for storing the preset information and the acquired data through the memory;
the voice prompt module is connected with the central control module and used for carrying out voice playing on the received information and the running state through the voice broadcaster;
and the display module is connected with the central control module and used for displaying the acquired images and voice instructions through the display screen.
2. The intelligent robot control system of claim 1, wherein the camera module comprises:
the image acquisition unit is used for acquiring images through the camera;
the illumination compensation unit is used for synchronously moving with the camera through the LED light supplement lamp and performing illumination compensation on the image acquisition position of the camera;
and the angle adjusting unit is used for connecting the camera with the robot main body and adjusting and controlling the orientation of the lens of the camera through the angle adjusting device.
3. The intelligent robot control system of claim 1, wherein the image recognition module comprises:
the preset information storage unit is used for pre-storing the specific limb action image information to obtain a data set;
the characteristic extraction unit is used for extracting the characteristics of the limb action information in the collected image information;
and the instruction judging unit is used for comparing the extracted body action information characteristics with preset information in a preset data set, determining action instruction information corresponding to the extracted body action information characteristics, and outputting the action instruction information to the central control module.
4. The robotic intelligence control system of claim 1 wherein the position location module comprises:
the three-dimensional view construction unit is used for collecting surrounding images through the camera when the robot is placed in a new environment to construct a three-dimensional view;
the position image identification unit is used for comparing the acquired environment image of the real-time position with the image in the constructed three-dimensional view to determine the position of the robot;
and the position point marking unit is used for marking position points in the three-dimensional view according to the real-time position of the robot and transmitting the position points to the remote monitoring terminal through wireless signals.
5. The intelligent robot control system of claim 1, wherein the speech recognition module employs a recognition method comprising:
(1) extracting acoustic characteristics of each voice frame; training a progressive double-output neural network model by using samples of clean voice and noise voice, estimating ideal soft masking of each voice frame by using the trained progressive double-output neural network model, and performing enhancement processing on acoustic characteristics; if the method is applied to human ears, the waveform is reconstructed by using the enhanced acoustic features to obtain a waveform capable of being subjectively listened; if the method is applied to a voice recognition system, applying the estimated ideal soft masking to the acoustic features of the input voice to obtain masked acoustic features, and then reconstructing the waveform to obtain enhanced voice;
(2) acquiring an original learning data set relating to the recognition target language, wherein each original learning data included in the original learning data set includes learning-use voice data and text information corresponding to the learning-use voice data; constructing a target tag by separating text information included in the respective original learning data in units of letters;
(3) an acoustic model based on a deep neural network is constructed by learning speech data for learning and a target label corresponding to the learning speech data included in the respective pieces of original learning data, wherein different letters among the letters included in the target label are defined as classes different from each other in the acoustic model, and even if the same letter is included, the same letter is defined as a class different from each other when the arrangement position is different.
6. The robotic intelligence control system of claim 5 wherein the step of constructing the acoustic model comprises:
(3.1) updating the weighting values of the deep neural network constituting the acoustic model using a connection timing classification method;
(3.2) the deep neural network comprises at least one of a recurrent neural network, a bidirectional recurrent neural network, a long-short term memory, a bidirectional long-short term memory, a gated cyclic unit, and a bidirectional gated cyclic unit.
7. The intelligent robot control system of claim 1, wherein the obstacle avoidance module is configured to perform the following obstacle avoidance method:
1) when the robot detects that an obstacle exists, acquiring parameter information of the obstacle; determining a first height value and a second height value of the obstacle, wherein the first height value is the distance between the highest point of one end, close to the robot, of the obstacle and the ground, and the second height value is the distance between the highest point of one end, far away from the robot, of the obstacle and the ground;
2) and controlling the robot to execute obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot according to the parameter information of the obstacle, the size relation between the first height value and the preset threshold value, and the size relation between the second height value and the preset threshold value, and the current working mode of the robot.
8. The intelligent robot control system according to claim 7, wherein the controlling the robot to perform the obstacle avoidance operation corresponding to the parameter information of the obstacle and the current working mode of the robot according to the magnitude relationship between the parameter information of the obstacle, the first height value, the second height value, and the preset threshold value, and the current working mode of the robot comprises:
2.1) determining the type of the obstacle according to the parameter information of the obstacle, the size relationship between the first height value and the preset threshold value, the size relationship between the second height value and the preset threshold value and the current working mode of the robot;
2.2) controlling the robot to execute obstacle avoidance operation corresponding to the type of the obstacle according to the determined type of the obstacle.
9. The intelligent robot control system according to claim 8, wherein the parameter information of the obstacle, the magnitude relationship between the first height value and the second height value, and the preset threshold value, and the current working mode of the robot, and the determining the type of the obstacle comprises:
when the current working mode of the robot is a mopping mode or a sweeping and mopping integrated mode, if the height of the obstacle is smaller than a first preset height, determining that the type of the obstacle is a stridable obstacle, and if the height of the obstacle is larger than or equal to the first preset height, determining that the type of the obstacle is a non-stridable obstacle;
when the current working mode of the robot is a mopping mode or a sweeping and mopping integrated mode, if the inclination angle of the obstacle is smaller than a first preset angle, determining that the type of the obstacle is a stridable obstacle, and if the inclination angle of the obstacle is larger than or equal to the first preset angle, determining that the type of the obstacle is a non-stridable obstacle;
when the current working mode of the robot is a sweeping mode, if the height of the obstacle is smaller than a second preset height, determining that the type of the obstacle is a stridable obstacle, and if the height of the obstacle is larger than or equal to the second preset height, determining that the type of the obstacle is a non-stridable obstacle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010598446.4A CN111775151A (en) | 2020-06-28 | 2020-06-28 | Intelligent control system of robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010598446.4A CN111775151A (en) | 2020-06-28 | 2020-06-28 | Intelligent control system of robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111775151A true CN111775151A (en) | 2020-10-16 |
Family
ID=72760652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010598446.4A Pending CN111775151A (en) | 2020-06-28 | 2020-06-28 | Intelligent control system of robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111775151A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112487872A (en) * | 2020-11-10 | 2021-03-12 | 河北工业大学 | Obstacle avoidance control method and control system of intelligent mowing robot |
| CN112712175A (en) * | 2020-12-30 | 2021-04-27 | 广州富港万嘉智能科技有限公司 | Robot learning method and related device |
| CN112975964A (en) * | 2021-02-23 | 2021-06-18 | 青岛海科虚拟现实研究院 | Robot automatic control method and system based on big data and robot |
| CN113400279A (en) * | 2021-06-03 | 2021-09-17 | 南京机器人研究院有限公司 | Industrial robot visual detection and obstacle avoidance system |
| CN113771066A (en) * | 2021-09-07 | 2021-12-10 | 合肥学院 | Motor self-learning control system based on intelligent robot |
| WO2023142711A1 (en) * | 2022-01-27 | 2023-08-03 | 追觅创新科技(苏州)有限公司 | Robot control method and device, and robot and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1513645A (en) * | 2002-12-31 | 2004-07-21 | 中国科学院自动化研究所 | Intelligent autonomous wheel type mobile robot |
| JP2006123153A (en) * | 2004-11-01 | 2006-05-18 | Advanced Telecommunication Research Institute International | Development support device and development support program for communication robot |
| CN106325094A (en) * | 2016-10-30 | 2017-01-11 | 苏州市克拉思科文化传播有限公司 | Smart home management sweeping robot |
| CN109215637A (en) * | 2017-06-30 | 2019-01-15 | 三星Sds株式会社 | Audio recognition method |
| CN110502014A (en) * | 2019-08-22 | 2019-11-26 | 深圳乐动机器人有限公司 | A kind of method and robot of robot obstacle-avoiding |
| CN110767244A (en) * | 2018-07-25 | 2020-02-07 | 中国科学技术大学 | Speech enhancement method |
-
2020
- 2020-06-28 CN CN202010598446.4A patent/CN111775151A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1513645A (en) * | 2002-12-31 | 2004-07-21 | 中国科学院自动化研究所 | Intelligent autonomous wheel type mobile robot |
| JP2006123153A (en) * | 2004-11-01 | 2006-05-18 | Advanced Telecommunication Research Institute International | Development support device and development support program for communication robot |
| CN106325094A (en) * | 2016-10-30 | 2017-01-11 | 苏州市克拉思科文化传播有限公司 | Smart home management sweeping robot |
| CN109215637A (en) * | 2017-06-30 | 2019-01-15 | 三星Sds株式会社 | Audio recognition method |
| CN110767244A (en) * | 2018-07-25 | 2020-02-07 | 中国科学技术大学 | Speech enhancement method |
| CN110502014A (en) * | 2019-08-22 | 2019-11-26 | 深圳乐动机器人有限公司 | A kind of method and robot of robot obstacle-avoiding |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112487872A (en) * | 2020-11-10 | 2021-03-12 | 河北工业大学 | Obstacle avoidance control method and control system of intelligent mowing robot |
| CN112712175A (en) * | 2020-12-30 | 2021-04-27 | 广州富港万嘉智能科技有限公司 | Robot learning method and related device |
| CN112712175B (en) * | 2020-12-30 | 2024-02-23 | 广州富港生活智能科技有限公司 | Robot learning method and related device |
| CN112975964A (en) * | 2021-02-23 | 2021-06-18 | 青岛海科虚拟现实研究院 | Robot automatic control method and system based on big data and robot |
| CN112975964B (en) * | 2021-02-23 | 2022-04-01 | 青岛海科虚拟现实研究院 | Robot automatic control method and system based on big data and robot |
| CN113400279A (en) * | 2021-06-03 | 2021-09-17 | 南京机器人研究院有限公司 | Industrial robot visual detection and obstacle avoidance system |
| CN113400279B (en) * | 2021-06-03 | 2022-05-10 | 南京机器人研究院有限公司 | Industrial robot visual detection and obstacle avoidance system |
| CN113771066A (en) * | 2021-09-07 | 2021-12-10 | 合肥学院 | Motor self-learning control system based on intelligent robot |
| WO2023142711A1 (en) * | 2022-01-27 | 2023-08-03 | 追觅创新科技(苏州)有限公司 | Robot control method and device, and robot and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111775151A (en) | Intelligent control system of robot | |
| US11216954B2 (en) | Systems and methods for real-time adjustment of neural networks for autonomous tracking and localization of moving subject | |
| CN100360204C (en) | Control system of intelligent perform robot based on multi-processor cooperation | |
| CN109571513B (en) | Immersive mobile grabbing service robot system | |
| CN108406848A (en) | A kind of intelligent robot and its motion control method based on scene analysis | |
| CN111026873B (en) | Unmanned vehicle and navigation method and device thereof | |
| KR102663375B1 (en) | Apparatus and method for automatically focusing the audio and the video | |
| CN109933191B (en) | Gesture recognition and control method and system | |
| CN112135553A (en) | Method and apparatus for performing cleaning operations | |
| CN114683290B (en) | Method and device for optimizing pose of foot robot and storage medium | |
| JP2022507635A (en) | Intelligent vehicle motion control methods and devices, equipment and storage media | |
| CN111098307A (en) | Intelligent patrol robot | |
| Zhu et al. | An edge computing platform of guide-dog robot for visually impaired | |
| CN113056315B (en) | Information processing apparatus, information processing method, and program | |
| Zhang et al. | Robotic control of dynamic and static gesture recognition | |
| CN111695408A (en) | Intelligent gesture information recognition system and method and information data processing terminal | |
| CN104575489A (en) | Robot identification system | |
| KR20210048271A (en) | Apparatus and method for performing automatic audio focusing to multiple objects | |
| CN209734484U (en) | Intelligent blind guiding device | |
| CN114453852A (en) | Method and system for controlling mechanical arm to assemble blade based on voice recognition | |
| CN113478485A (en) | Robot, control method and device thereof, electronic device and storage medium | |
| CN112847374A (en) | Parabolic-object receiving robot system | |
| CN111590576A (en) | Disaster relief robot in nuclear radiation environment | |
| CN117086871B (en) | Open robot interaction control system | |
| CN118092674B (en) | Gesture control method and system for ROV |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201016 |
|
| RJ01 | Rejection of invention patent application after publication |